Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90097
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     等
    -0.09
     जैसे
    -0.09
     వంటి
    -0.08
     സു�
    -0.08
     zoals
    -0.08
     Like
    -0.08
     συνεχ
    -0.07
    .allocate
    -0.07
     যেমন
    -0.07
    ুল
    -0.07
    POSITIVE LOGITS
     cemetery
    0.08
     непод
    0.08
    -bottom
    0.08
     collars
    0.08
     ordin
    0.07
     currents
    0.07
     stadium
    0.07
     земле
    0.07
     perpendicular
    0.07
     plaques
    0.07
    Activations Density 0.015%

    No Known Activations